Computational Intelligence最新文献

Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well-organized with a hierarchical structure in real-world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, the most existing methods perform event detection in Euclidean space, which cannot adequately represent hierarchical relationships. To address these issues, we propose a novel event detection network HyperED which embeds the event context and types in Poincaré ball of hyperbolic geometry to help learn hierarchical features between events. Specifically, for the event detection context, we first leverage the pre-trained BERT or BiLSTM in Euclidean space to learn the semantic features of ED sentences. Meanwhile, to make full use of the dependency knowledge, a GNN-based model is applied when encoding event types to learn the correlations between events. Then we use a simple neural-based transformation to project the embeddings into the Poincaré ball to capture hierarchical features, and a distance score in hyperbolic space is computed for prediction. The experiments on MAVEN and ACE 2005 datasets indicate the effectiveness of the HyperED model and prove the natural advantages of hyperbolic spaces in expressing hierarchies in an intuitive way.

At present, most of the resource allocation methods in mobile edge computing allocate computing resources according to the time order in which task requests are calculated and unloaded, without considering the priority of tasks in practical applications. According to the computing requirements in such cases, a priority task-oriented resource allocation method is proposed. According to the average processing time of the task execution, the corresponding priority for task is given. The tasks with different priorities are weighted to allocate computing resources, which not only ensures that the high-priority tasks obtain sufficient computing resources, but also reduces the total time and energy consumption to complete the calculation of all tasks, thus improving the quality of service. The experimental results show that the proposed method can achieve better performance.

This article investigates the use of unmanned aerial vehicles (UAVs) in assisting hybrid non-orthogonal multiple access (NOMA) systems to enhance spectrum efficiency and communication connectivity. A joint optimization problem is formulated for UAV positioning and user grouping to maximize the sum rate. The formulated problem exhibits non-convexity, calling for an effective solution. To address this issue, a two-stage approach is proposed. In the first stage, a particle swarm optimization algorithm is employed to optimize the UAV positions without considering user grouping. With the UAV positions optimized, a game theory-based approach is utilized in the second stage to optimize user grouping and improve the sum rate of the hybrid NOMA system. Simulation results demonstrate that the proposed two-stage method achieves solutions close to the global optimum of the original problem. By optimizing the positions of UAVs and user groups, the sum rate can be effectively improved. Additionally, optimizing the deployment of UAVs ensures better fairness in providing communication services to multiple users.

Indoor GPS location estimation encounters accuracy challenges from intricate building structures and diverse signal interferences. Trilateration methods utilising APs are typically employed to estimate indoor locations. Nevertheless, estimation errors from multipath effects and high power consumption of sensors employed in location estimation curtail battery life. To address this issue, research into location estimation methods utilising machine learning has been conducted. However, challenges involving the selection of the optimal access point locations and obtaining dense RSSI data have been noted. In this article presents a solution based on sparse radio maps for decreasing the expenses of collecting RSSI data while simultaneously enhancing indoor location accuracy through the integration of image data. The proposed approach integrates matrix-based RSSI indoor positioning (M-RIP) for initial location estimation and feature-based image indoor positioning (F-IIP) for position determination via image feature matching. Furthermore, extended area-based post-processing (EA-PP) is employed to augment M-RIP's precision and minimize image matching computation in F-IIP, improving overall performance. This article utilizes actual building data to validate the precision of the position estimation and efficiency of computation reduction using the proposed method.

This study introduces a comprehensive framework designed for detecting and mitigating fake and potentially threatening user communities within 5G social networks. Leveraging geo-location data, community trust dynamics, and AI-driven community detection algorithms, this framework aims to pinpoint users posing potential harm. Including an artificial control model facilitates the selection of suitable community detection algorithms, coupled with a trust-based strategy to effectively identify and filter potential attackers. A distinctive feature of this framework lies in its ability to consider attributes that prove challenging for malicious users to emulate, such as the established trust within the community, geographical location, and adaptability to diverse attack scenarios. To validate its efficacy, we illustrate the framework using synthetic social network data, demonstrating its ability to distinguish potential malicious users from trustworthy ones.

Hyperspectral images contain rich spatial and spectral information, which provides a strong basis for distinguishing different land-cover objects. Therefore, hyperspectral image (HSI) classification has been a hot research topic. With the advent of deep learning, convolutional neural networks (CNNs) have become a popular method for hyperspectral image classification. However, convolutional neural network (CNN) has strong local feature extraction ability but cannot deal with long-distance dependence well. Vision Transformer (ViT) is a recent development that can address this limitation, but it is not effective in extracting local features and has low computational efficiency. To overcome these drawbacks, we propose a hybrid classification network that combines the strengths of both CNN and ViT, names Spatial-Spectral Former(SSF). The shallow layer employs 3D convolution to extract local features and reduce data dimensions. The deep layer employs a spectral-spatial transformer module for global feature extraction and information enhancement in spectral and spatial dimensions. Our proposed model achieves promising results on widely used public HSI datasets compared to other deep learning methods, including CNN, ViT, and hybrid models.

In Visual question answering (VQA), a natural language answer is generated for a given image and a question related to that image. There is a significant growth in the VQA task by applying an efficient attention mechanism. However, current VQA models use region features or object features that are not adequate to improve the accuracy of generated answers. To deal with this issue, we have used a Two-way Co-Attention Mechanism (TCAM), which is capable enough to fuse different visual features (region, object, and concept) from diverse perspectives. These diverse features lead to different sets of answers, and also, there is an inherent relationship between these visual features. We have developed a powerful attention mechanism that uses these two critical aspects by using both bottom-up and top-down TCAM to extract discriminative feature information. We have proposed a Collective Feature Integration Module (CFIM) to combine multimodal attention features and thus capture the valuable information from these visual features by employing a TCAM. Further, we have formulated a Vertical CFIM for fusing the features belonging to the same class and a Horizontal CFIM for combining the features belonging to different types, thus balancing the influence of top-down and bottom-up co-attention. The experiments are conducted on two significant datasets, VQA 1.0 and VQA 2.0. On VQA 1.0, the overall accuracy of our proposed method is 71.23 on the test-dev set and 71.94 on the test-std set. On VQA 2.0, the overall accuracy of our proposed method is 75.89 on the test-dev set and 76.32 on the test-std set. The above overall accuracy clearly reflecting the superiority of our proposed TCAM based approach over the existing methods.

The curse of high dimensionality in text classification is a worrisome problem that requires efficient and optimal feature selection (FS) methods to improve classification accuracy and reduce learning time. Existing filter-based FS methods evaluate features independently of other related ones, which can then lead to selecting a large number of redundant features, especially in high-dimensional datasets, resulting in more learning time and less classification performance, whereas information theory-based methods aim to maximize feature dependency with the class variable and minimize its redundancy for all selected features, which gradually becomes impractical when increasing the feature space. To overcome the time complexity issue of information theory-based methods while taking into account the redundancy issue, in this article, we propose a new feature selection method for text classification termed correlation-based redundancy removal, which aims to minimize the redundancy using subsets of features having close mutual information scores without sequentially seeking already selected features. The idea is that it is not important to assess the redundancy of a dominant feature having high classification information with another irrelevant feature having low classification information and vice-versa since they are implicitly weakly correlated. Our method, tested on seven datasets using both traditional classifiers (Naive Bayes and support vector machines) and deep learning models (long short-term memory and convolutional neural networks), demonstrated strong performance by reducing redundancy and improving classification compared to ten competitive metrics.

A gap among the people has been created due to a lack of social interactions. The physical void has led to an increase in online interaction among users on social media platforms. Sentiment analysis of such interactions can help us analyze the general public psychology during the pandemic. However, the lack of data in non-English and low-resource languages like ‘Hindi’ makes it difficult to study it among native and non-English speaking masses. Here, we create a small collection of ‘Hindi’ tweets on COVID-19 during the pandemic containing 10,011 tweets for sentiment analysis, which is named as sentiment analysis for Hindi (SAFH). In this article, we describe the process of collecting, creating, annotating the corpus, and sentiment classification. The claims have been verified using different word embedding with a deep learning classifier through the proposed model. The achieved accuracy of the proposed model yields up to a permissible rate of 90.9%.

The manufacturing industry is always exploring techniques to optimize processes, increase product quality, and more accurately identify defects. The technique of deep learning is the strategy that will be used to handle the issues presented. However, the challenge of using AI in this domain is the small and imbalanced dataset for training affected by the severe shortage of defective data. Moreover, data acquisition requires significant labor, time, and resources. In response to these demands, this research presents an intelligent internet of things (IoT) framework enriched by generative adversarial network (GAN). This framework was developed in response to the needs outlined above. The framework applies the IoT for real-time data collection and communication, while GAN are utilized to synthesize high-fidelity images of manufacturing defects. The quality of the GAN-synthesized image is quantified by the average FID score of 8.312 for non-defective images and 7.459 for defective images. As evidenced by the similarity between the distributions of synthetic and real images, the proposed generative model can generate visually authentic and high-fidelity images. As demonstrated by the results of the defect detection experiments, the accuracy can be enhanced to the maximum of 96.5% by integrating the GAN-synthesized images with the real images. Concurrently, this integration reduces the occurrence of false alarms.